© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 16263
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases with objects

    np_acts-logits-general · gemini-2.5-flash-lite

    zero-day exploits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ristown
    0.54
    ol
    0.53
    )$-
    0.51
    Tous
    0.49
    oland
    0.48
    od
    0.47
     którym
    0.47
    ómago
    0.47
    नैतिक
    0.47
     För
    0.46
    POSITIVE LOGITS
     ши
    0.51
    _*
    0.50
     stitch
    0.49
     condomin
    0.48
     помещения
    0.46
     обы
    0.46
     caus
    0.45
     cadence
    0.45
    _
    0.45
     pune
    0.45
    Activations Density 0.000%

    No Known Activations